BriefGPT.xyz
May, 2023
基于生成对抗网络的皮损分割
Generative Adversarial Networks based Skin Lesion Segmentation
HTML
PDF
Shubham Innani, Prasad Dutande, Bhakti Baheti, Venu Pokuri, Ujjwal Baid...
TL;DR
使用对抗学习的算法开发的可自动生成皮肤病变掩膜的 EGAN 算法,可应用于皮肤癌病变的计算机辅助诊断,其精度比当前最先进的基于皮损分割的方法高出2%的Dice系数,1%的Jaccard相似度,和1%的准确度。
Abstract
skin cancer
is a serious condition that requires accurate identification and treatment. One way to assist clinicians in this task is by using
computer-aided diagnosis
(CAD) tools that can automatically segment sk
→